Menu
Sprawdź status swojego zamówienia
Skontaktuj się z nami
Książka Biologically Inspired Hexagonal Deep Learning for Hexagonal Image Processing Tobias Schlosser

Biologically Inspired Hexagonal Deep Learning for Hexagonal Image Processing

Autor: Tobias Schlosser
Język: Angielski
Oprawa: Miękka
Wydawca: Technische Universität Chemnitz
Dostępność: Na zamówienie
Wysyłamy za 17-27 dni
139.19 zł
While current approaches to digital image processing in the context of deep learning are motivated b...

Informacje o książce

Autor
Tobias Schlosser
Język
Angielski
Oprawa
Książka - Miękka
Data wydania
2024
strony
300
EAN
9783961002139
ISBN
3961002134
Enbook ID
46067565
Wydawca
Technische Universität Chemnitz
Waga
438
Wymiary
148 x 210 x 19

Pełny opis

While current approaches to digital image processing in the context of deep learning are motivated by biological processes in the human brain, they are, however, also limited due to the current state of the art of input and output devices. To generate images from real-world scenes, the underlying lattice formats are predominantly based on rectangular or square structures. Yet, the human visual perception system suggests an alternative approach that manifests itself in the sensory cells of the human eye in the form of hexagonal arrangements.This contribution is therefore concerned with the design, implementation, and evaluation of hexagonal solutions in the form of hexagonal deep neural networks (H-DNN). The realized hexagonal functionality had to be built from the ground up as hexagonal counterparts to otherwise conventional square image processing systems, for which hexagonal equivalents for artificial neural network operations, layers, and models had to be implemented.To enable their evaluation, a set of different application areas within astronomical, medical, and industrial image processing are provided that allow an assessment of H-DNNs in terms of their general performance. The presented results demonstrate the possible benefits of H-DNNs for image processing systems. It is shown that H-DNNs can result in increased classification capabilities given different basic geometric shapes and contours, which in turn partially translate into their real-world applications.

Możesz być zainteresowany

Unreal Engine 5 Game Development with C++ Scripting: Become a professional game developer and create fully functional, high-quality games

Zhenyu George Li
199.98 zł

Healthcare Policy in Africa

Jean-Germain Gros
242.29 zł

Unreal Engine Pro

Frahaan Hussain
118.37 zł

Multiplayer Game Development with Unreal Engine 5: Create compelling multiplayer games with C++, Blueprints, and Unreal Engine's networking features

Marco Secchi
188.31 zł

Principles of Endodontics

Shanon Patel
257.57 zł

Installation Methods of Offshore Oil-Gas Well Conductor

Jin Yang
423.12 zł

Computer Vision, Graphics, and Image Processing

Snehasis Mukherjee
212.24 zł

Father Sergius

Leo Tolstoy
30.92 zł

Oracle Stored Programs for Beginners: Creating Your Own Procedures and Functions in PL/SQL

Djoni Darmawikarta
43.47 zł

Unreal Engine 4 Scripting with C++ Cookbook

William Sherif
231.21 zł

Unity of Reason

Dieter Henrich
480.32 zł

Hexagonal Image Processing

Jayanthi Sivaswamy
423.12 zł

Hexagonal Image Processing

Jayanthi Sivaswamy
423.12 zł

Klienci, którzy kupili tę książkę, kupili również

Il linfodrenaggio per la tua salute. L'automassaggio contro cellulite, edemi, gonfiori

Dorothea Schneider Siemens
46.39 zł

Raumausstattermeister - Das prufungsrelevante Wissen

Sarastro Verlag
181.50 zł

Poslanie vášho života

Stephen R. Covey
41.91 zł

Frozen - Anna e Elsa 7 - L'ammiratore segreto

Disney
16.33 zł

Vanitas 2 - Magická kniha

Džun Močizuki
33.45 zł